Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2053 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1591085 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1618961 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.4198. Min Act: -0.0001

Data Index: 1377996 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.4116. Min Act: -0.0001

Data Index: 1516492 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1404604 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1449641 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2932. Min Act: -0.0001

Data Index: 1654760 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2882. Min Act: -0.0001

Data Index: 1366493 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3629. Min Act: -0.0001

Data Index: 1435354 (Python Code)

Max Activating Token Index: 793

Text #9

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3073. Min Act: -0.0001

Data Index: 1458485 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1632806 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1584331 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1429770 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1460772 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1513043 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1648724 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1613863 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1772. Min Act: -0.0001

Data Index: 1520871 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2512. Min Act: -0.0001

Data Index: 1418354 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1652526 (Python Code)

Max Activating Token Index: 916